INDEX

Explanations

references to quantities and observations regarding various subjects

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Follows "were", "those", "these", "also", or "are"

np_acts-logits-general · gemini-2.0-flash

existential or quantifying words followed by nouns

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 stuff

-1.17

 legislation

-0.99

stuff

-0.93

 Stuff

-0.92

Stuff

-0.91

 STUFF

-0.86

 evidence

-0.81

 verksamhet

-0.80

legislation

-0.79

 equipment

-0.79

POSITIVE LOGITS

 CreateTagHelper

0.81

 kasarigan

0.77

Autoritní

0.77

MemoryWarning

0.76

رشف

0.75

 للاسماء

0.74

Datuak

0.73

ConstraintMaker

0.72

 mergeFrom

0.72

 مشين

0.72

Activations Density 0.938%

references to quantities and observations regarding various subjects

Follows "were", "those", "these", "also", or "are"

existential or quantifying words followed by nouns

No Comments

No Known Activations